Background. Shewhart was the first to describe the possibilities that come with having a statistically robust process in 1924. Since his discovery, the importance of a robust process became more apparent and together with the consequences of an unstable process. A firm with a manufacturing process that is out of statistical control tends to waste money, increase risks, and provide an uncertain quality to its customers. The framework of Statistical Quality Control has been developed since its founding, and today it is a well-established tool used in several industries with successful results. When it was first thought of, complicated calculations had to be performed and was performed manually. With digitalisation, the quality tools can be used in real-time, providing high-precision accuracy on the quality of the product. Despite this, not all firms nor industries have started using these tools as of today.    The costs that occur in relation to the quality, either as a consequence of maintaining good quality or that arises from poor quality, are called Cost of Quality. These are often displayed through one of several available cost models. In this thesis, we have created a cost model that was heavily inspired by the P-A-F model. Several earlier studies have shown noticeable results by using SPC, COQ or a combination of them both.     Objectives. The objective of this study is to determine if cost optimisation could be utilised through SQC implementation. The cost optimisation is a consequence of an unstable process and the new way of thinking that comes with SQC. Further, it aims to explore the relationship between cost optimisation and SQC. Adding a layer of complexity and understanding to the spread of Statistical Quality Tools and their importance for several industries. This will contribute to tightening the bonds of production economics, statistical tools and quality management even further.   Methods. This study made use of two closely related methodologies, combining SPC with Cost of Quality. The combination of these two hoped to demonstrate a possible cost reduction through stabilising the process. The cost reduction was displayed using an optimisation model based on the P-A-F (Prevention, Appraisal, External Failure and Internal Failure) and further developed by adding a fifth parameter for optimising materials (OM). Regarding whether the process was in control or not, we focused on the thickness of the PVC floor, 1008 data points over three weeks were retrieved from the production line, and by analysing these, a conclusion on whether the process was in control could be drawn.    Results. Firstly, none of the three examined weeks were found to be in statistical control, and therefore, nor were the total sample. Through the assumption of the firm achieving 100% statistical control over their production process, a possible cost reduction of 874 416 SEK yearly was found.    Conclusions. This study has proven that through focusing on stabilising the production process and achieving control over their costs related to quality, possible significant yearly savings can be achieved. Furthermore, an annual cost reduction was found by optimising the usage of materials by relocating the ensuring of thickness variation from post-production to during the production.